Skip to content

Decision-Focused Learning for Mean-Variance Portfolio Optimization via KKT-Based Reformulation

Sep 2026 · 0 citations · 21 references
Computer Science

TL;DR

This work proposes a single-level optimization formulation that incorporates the Karush-Kuhn-Tucker optimality conditions of the lower-level MVO into the upper-level learning problem, and explicitly preserves the budget and short-sale constraints while remaining tractable for standard nonlinear optimization solvers.

Abstract

Mean-variance portfolio optimization (MVO) is a central framework in data-driven asset management. A widely adopted approach is a two-stage framework that first predicts expected returns and then solves the optimization problem based on these predictions, with the predictive models trained by minimizing prediction errors. However, this objective of prediction is not aligned with the quality of the downstream portfolio decision. Decision-focused learning (DFL), which directly minimizes the downstream decision loss within the learning process, has thus emerged as a promising direction. However, existing DFL approaches to MVO rely on surrogate losses or constraint relaxations for tractability, creating a structural mismatch between predictive model training and the constrained MVO solved at evaluation. We propose a single-level optimization formulation that incorporates the Karush-Kuhn-Tucker (KKT) optimality conditions of the lower-level MVO into the upper-level learning problem. This formulation explicitly preserves the budget and short-sale constraints while remaining tractable for standard nonlinear optimization solvers. Rolling-window experiments on real-world ETF (Exchange Traded Funds) data across two asset universes with different correlation structures show that our method achieved the best performance on multiple investment metrics and also demonstrated performance improvement due to the proposed regularization.

View source

Similar papers

Open access Aug 2026

Decision-Driven Regularization: A Blended Model for Learning and Optimization

This paper proposes a biobjective formulation that balances prediction accuracy and cost minimization, termed decision-driven regularization, which is shown to be numerically superior to other benchmarks, such as ordinary least squares, random forest, XGBoost, SPO+, perturbation gradient, and learning and rank, in the...

G. Loke, Qin-Shen Tang, Yangge Xiao et al. · 1 citation
Open access Sep 2026

Data-Driven Portfolio Optimization Using a Predict-Then-Optimize Framework

Effective portfolio diversification remains a central challenge in quantitative asset management. In this study, we propose a data-driven framework based on the predict-then-optimize (PO) paradigm, which combines return forecasting with portfolio allocation in a sequential manner. The forecasting module employs DLinear...

Yi Wang, Takashi Hasuike · 0 citations
Preprint Aug 2026

Dynamic Portfolio Optimization under CVaR Constraints

This work exploits the auxiliary-threshold representation of CVaR to establish the existence of an optimal strategy and strong duality without requiring market completeness, and proves that the resulting strategies converge to the optimal control as the number of iterations tends to infinity.

An-Ran Hu, Silvana M. Pesenti, Xiaofei Shi · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.